tsdae-civic-bert / README.md
ar9av's picture
Add new SentenceTransformer model
19a5ed9 verified
metadata
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - dense
  - generated_from_trainer
  - dataset_size:10000
  - loss:DenoisingAutoEncoderLoss
base_model: google-bert/bert-base-uncased
widget:
  - source_sentence: >-
      . the land and management meeting of 5th is 7:01 the order Um, is roll .
      we have us, Nicole, and, . Uh, the is the of of October, . Do have,, are
      there any, All right,, all favor approving your that is Um to
      participation Is would like see Miss> hear>> Yes,>>,>, so I'm sorry uh
      echoing? we . We hear little echo, but we you . Uh f first all, record,
      Diane Uh
    sentences:
      - >-
        All right. Good evening and welcome to

        the land use and building management

        committee meeting of November 5th, 2025. It is 7:01 and I am calling the
        meeting

        to order. Um, first item is roll call. Tonight we have with us council
        members

        Jim Fyer, Nicole Edy, Nicole Ays, and

        myself, Barbara Smith. Uh, next item on the agenda is the

        acceptance of the minutes of our meeting

        of October 1, 2025. Do I have a motion,

        Miss Edy, um, are there any corrections,

        All right, seeing none, all in favor of

        approving the minutes, please raise your

        Okay, that is unanimous. Um, moving on to public participation. Is there
        anyone

        here who would like to speak? I see Miss

        >> Yes, good. Can you hear me? >> Yes, we can. >> Yes, we can. >> I am
        in a hallway, so I'm sorry for any

        uh echoing. I hope it's Can you still

        understand me? >> Yes, we can. We hear a little echo, but

        we can still hear you. Uh anyway, f first of all, good evening. For the
        record, my name is Diane

        Laurisella. Uh
      - >-
        I'll now call to order the November 6, 2025 meeting of Mayor and
        Council. I'm going to call on the Mayor Pro Tem Andy Gibbs to lead us in
        prayer. Please remain standing for the pledge. Body heads, please. Dear
        me, Father, just thank you for this evening. Thank you for bringing us
        all together. Lord, I just ask you that as we look at the different
        things on our agenda tonight, that you help us to make the best decision
        for our community to move to move our community forward. Lord, I just
        ask you, Lord, to continue to put your arms around us for protection. To
        put your arms around us, your protection. I thank you, Lord, for sending
        your son to die on the cross for our sins, Lord. I thank you for the
        things that you've given us in our life, the mercy of the grace that
        you've extended to us each and every day to allow us to be able to wake
        up and walk among other people and help us to serve others as you want
        us to serve, Lord. And I thank you for everything you do for us. Your
        name, I pra
      - >-
        In the NOSERT room today, the link can be found on the Town of Orleans
        website. And calling the meeting to order. Any agenda changes? None this
        evening, this afternoon, sorry. Is there anyone for citizens speak? No
        one additional online. Okay, seeing none, we're going to go into
        priority business and we are going to start with our assistant
        superintendent. Wonderful. Thank you very much. Thank you. So I'm here
        today to share two things, our homeschooling process and then just an
        update on our grant. We can't hear you. Yeah. So sorry to enter. I was
        just going to interrupt. Just make sure that you pull this mic up and
        for everybody. Is this better? Okay, Parker. Sorry about that. Sorry. So
        I'm here today. Thank you for that. Just to talk about our homeschooling
        process and our grant process as well. So I'll go over our homeschooling
        process. I know of detailed information in the memo and I've included
        some links to our forms so you'll be able to see it and I'll just give a
        high-level ov
  - source_sentence: >-
      Um, and think these looking perhaps some feedback from what issues that
      need And you know just a the formula ., it based did work 1990 so and've
      and that address then uh they did student act was meant uh needs your
      communities urban Right now though large with towns . where are being
      because need of bill . especially the you'm to little . when hold harmless
      and you it certified would t
    sentences:
      - |-
        Um, and so I think these are the minds
        that they're looking to perhaps get some
        feedback from about what are the the
        issues that need to be tackled. And I
        think that, you know, just a couple
        things about the funding formula. Look,
        it's based based they did the work back
        in 1990 or so and they've made
        adjustments and they've made made
        probably two I think primary adjustments
        since that time. One was to address
        vocational needs and then uh they did
        the student opportunity act which was
        meant to address uh the needs of
        students in uh your gateway communities
        in urban areas. Right now though,
        there's a large contingent of districts
        in with towns such as Rutland, Paxton,
        Hold it. Um where they are being asked
        because of this old formula, you need to
        put more of the bill. Um and then
        especially in the context, and I know
        you asked this question, I'm going to
        talk about it a little bit. Um when
        districts fall into hold harmless, and
        you know, it hasn't been certified
        officially, but I would t
      - >-
        Good evening and welcome to the uh

        November 5th board meeting of the Topeka

        Development Corporation Board of

        Directors. I'll call this meeting to

        If we could stand for the pledge of

        allegiance, please. I pledge algiance to the flag of the

        United States of America and to the

        republic for which it stands. One nation

        under God, indivisible, with liberty and

        justice for all. >> Okay. Madame clerk, could call the role,

        >> President Padilla,

        >> here. Vice President Dolbler

        >> Directors Hiller

        >> here. Banks

        and Hoer

        >> All right. We have seven present. Seven present. We'll move on to
        item

        number four on the agenda. Madam Clerk,

        >> for approval of the August 12, 2025

        meeting minutes. >> Okay. I hope uh everyone has had an

        opportunity to look at the minutes

        from August meeting. >> Motion to approve by Councilman Banks,

        second by Councilman Miller. Take the

        roll call, please. >> All right. Uh President Padilla

        >> here. I Yes. Vic
      - >-
        You seem loud today. All right, it's 8 a.m. I'll go ahead and call this
        meeting to order. Today is Tuesday, November 8th, the meeting in the
        formal boardroom with the Genoaxi Public Service Center. First on our
        agenda are minutes. We have none and no claims. All right, great. We'll
        move right into our regular agenda. The board will meet with elected
        officials and the department heads discuss the following topics. We'll
        start with fiscal year 2027 budget calendar initiatives and guidelines.
        Good morning, Sarah. Good morning, Sarah Barrows, Budget Director. The
        board asked that we just go over a few things for the FY27 budget. Kind
        of hard to believe we're already there, but it is time. We met yesterday
        with the board and talked about some guidelines and initiatives that
        they could include for the FY27 budget. A lot of them you'll be very
        familiar with. 25% ending fund balance, things like that. The one thing
        that they have yet to discuss tomorrow is the placeholder that we'll
        include fo
  - source_sentence: >-
      we're of . That is year a good time, think's . So let's get back So we're
      having it quickly first ring . think they got the picture . I if of know
      we're to go this Each and every have the handout given you, City of Ridge
      fiscal year 2026 . If, . You again,'ll revising it You guys will of next
      with Mandy, there anything we need do Speak Mandy got a said ca us sorry
      Council disagrees me you scheduled to adopt a 2026
    sentences:
      - >-
        So, I'd like to make a motion to come

        out of non-public session. >> Okay, we have a motion to come out of

        non-public and a second. All in favor? I

        >> opposed. Okay, motion carries. 70. >> Um, and I'd also like to make a
        motion

        to seal the minutes indefinitely. >> Second that. >> Motion to seal the
        minutes indefinitely

        and a second. Uh, all in favor? Any

        Great. Motion carry 70. >> Good evening. Welcome to the Jerry Town

        Council meeting for Tuesday, November

        4th, 2025. >> Mr. Chair, excuse me. If we could make

        sure everyone's microphone is turned on,

        green light at the base of the stem. Thank you. >> Everyone's microphone
        on. >> All right. council Spencer, please lead us pledge

        algiance to the flag of the United

        States of America to the republic for it

        stands one nation

        indivisible with liberty and justice for

        >> Thank you. Uh, prevent emergency exits

        in the back of the room. Mr. The Havens

        are glad to help you. Um,

        do a roll ca
      - >-
        I pledge allegiance to the flag of the

        United States of America to the republic

        for it stands one nationy

        and justice for all. Please remain standing for a moment of

        silent reflection for all the service

        men and women throughout the world and

        for those who have passed away in our

        community, especially our former mayor,

        David J. Wenszel. Thank you. >> Roll call, please. >> Mr. King,

        >> Mr. Schuster,

        >> Dr. Mr. Rothschild

        >> Mr. McCandrew

        >> Mr. Small

        >> Dispatch with three of the minutes. >> Third order 3A correspondence
        dated

        October 28th, 2025 from the Interite

        Bike Coalition Executive Director Kuba

        James regarding support for the downtown

        Scranton Walkability Streetscape

        project. 3B. Letters of support from

        local businesses for the walkability and

        streetscape project ordinances. 3C. Letter from Fire Tree Limited
        received

        October 27th, 2025 regarding residential

        re-entry center services. >> Are there any comments on any of the

        thir
      - >-
        Yeah, we're kind of talking about everything. That is. Any time of the
        year is a good time to catch fish. Okay, I think it's been about five
        minutes. So let's get started back. So we're having one next one. We're
        doing it quickly. So this is the first ring. I think they got the
        picture. Okay. Okay, I think if you can just kind of, I know we're not
        going to go over this. Each and every one of you in here should have the
        handout that's given to you, which says, City of Blue Ridge, proposed
        fiscal year budget for 2026. If you will, please take the opportunity.
        You know, this is, again, we'll be revising it. You guys will at the
        beginning of next year, hopefully, with better numbers. Mandy, is there
        anything we need to do with this tonight? Speak into the microphone,
        Mandy. I got a phone call that said they can't hear us. I'm sorry.
        Council does have an option, unless Chuck disagrees with me. I'm sorry
        to put you on the spot. You are scheduled to adopt a 2026 budget next
        week. I believe, I
  - source_sentence: >-
      The City Buffalo Planning ⚫ November 17, NY 14202 http //www.buffalony.gov
      Morrell Regular Planning Board 4:00 PM Hall, Sq., NY . called order 4:06
      PM by Vice Chairman Schwartz Name Absent   Cynthia Schwartz  Martha
      Scott Billman  Arthur      Samantha  Meeting be Via
      Videoconferencing and Anyone Wishes 912 City or Videoconferencing ., or
      Call 1-415-655-0001 Meeting 173 2665 Password PublicComment (Not for) II .
      Approval of Minutes 1 . - Meetin
    sentences:
      - >-
        THE CITY OF BUFFALO 
         
        The City of Buffalo Planning Board 

        912 City Hall 

        Minutes  November 17, 2025 
         
        Buffalo, NY 14202 
         
         
        http://www.buffalony.gov 
         
         
        James Morrell 

        Regular Planning Board Meeting 

        OSP Conference Room 

        4:00 PM 
         
        912 City Hall, 65 Niagara Sq., Buffalo, NY 14202 

        I. Call to Order 
         The meeting was called to order at 4:06 PM by Vice Chairman Cynthia Schwartz 
        Attendee Name 

        Present 

        Absent 

        Late 

        Arrived 

        James Morrell 

         

         

         
         
        Cynthia Schwartz 

         

         

         
         
        Martha Lamparelli 

         

         

         
         
        Scott Billman 

         

         

         
         
        Arthur Hall 

         

         

         
         
        Len Sciolino 

         

         

         
         
        Samantha Soltis 

         

         

         
         
        This Meeting Will be Held Via Videoconferencing and In-Person. Anyone
        who Wishes to Attend 

        May Do So in Room 912 City Hall or Via Videoconferencing. to Join
        Online, Go to 

        Www.Webex.Com or Call 1-415-655-0001; Meeting Number 173 504 2665
        Password: 

        PublicComment (Not Required for Phone) 

        II. Approval of Meeting Minutes 

        1. Planning Board - Regular Planning Board Meetin
      - >-
        p.m. and I'm calling the Hamilton

        Planning Board meeting to order. This meeting is being recorded. Uh to
        aid the transcriptionist, I'm

        going to take roles. So when I call your

        name, would you please indicate that

        you're present? Pat Norton,

        >> Jonathan Poor,

        >> Jonathan Poor, present. >> Amal Dawquist,

        >> Amal Dawquist, present. >> Darcy Dale,

        >> Darcy Dale, present. >> And Marne Crouch, present. And I note

        for the record that Beth her is absent. Um, her father passed away and
        we're

        very sorry to hear that. And, uh,

        perhaps Bill uh will uh appear. I know

        Matt Hamill, he was on the Cape, right? It's unlikely he'll be here and
        I don't

        believe we've heard from Jeff Austin. >> Uh the first item on our agenda
        is to

        review the minutes from October 21st. Um

        do I have a motion to approve those uh

        >> So So moved. >> Do I have a second? Any discussion about

        the minutes? >> Uh Darcy, I think you found a few typos. Yeah, just a
        coup
      - >-
        We the citizens of the city of Gilroy as

        we come to this room tonight as a

        complex human crowd carrying burdens,

        hope, joy, and trusting that you alone

        can hold us together. God, we pray for

        your love and your peace. Help us to

        trust you, Lord, more than our opinions,

        our fears, and even our accomplishments. May we turn to you for your
        truth. Lastly, fill us with grace, Lord, as

        these leaders make decisions tonight

        that will affect each one of us. Continue to remind us that all that
        this

        day is done, all that is done here this

        day and all that is accomplished is for

        the greater glory of you. Please bless

        these proceedings. We ask for these

        things in your name. Amen. Thank you. Thank you, pastor. Moving on to
        item

        1.6. Six. Orders of the day we have

        none. Moving on to item 1.7, employee

        Finance director Harjo Singha will

        introduce a new employee. Thank you. Thank you, Mayor. Um, tonight I
        have the

        privilege of introducing Naelli

        Martinez. Uh, she joins us in the

        utility billing team uh
  - source_sentence: >-
      right o'clock Oh Jack here . Man brought team 3rd November . going'll to .
      We Pledge of and . And we got guests Manager Brantley'll of . the . I
      appeal flag the United States of and to Republic which,, for . Let . God,
      come before this grateful live wonderful community We serve our community
      members in our respective capacities morning and give us eyes and full
      hearts, Lord, as handle business Thank you your, In Christ name amen Thank
      Price the pledge . First item is
    sentences:
      - >-
        All right, it's nine o'clock. Oh, Jack's here too. Man, y'all brought
        the whole team. 9 o'clock, November 3rd, November already. Gosh. Time
        keeps on going. We'll call the meeting to order. We'll open with the
        Pledge of Allegiance and prayer. And since we've got special guests,
        I'll ask Town Manager Brantley Price if he'll lead us in the Pledge of
        Allegiance. And I'll say the prayer. I appeal to the flag of the United
        States of America and to the Republic for which it stands, one nation
        under God, indivisible, with liberty and justice for all. Let's pray
        together. God, we come before you this morning with grateful hearts to
        live in such a wonderful community. We're grateful for the opportunity
        to serve our community members in our respective capacities here this
        morning. Be with us and give us clear eyes and full hearts, Lord, as we
        handle the people's business. Thank you for your many, many blessings.
        In Christ's name, amen. Amen. Thank you, Manager Price, for the pledge.
        First item is
      - >-
        Notice of Meeting of the

        Planning and Zoning Commission

        of the City of Georgetown, Texas

        November 4, 2025

        The Georgetown Planning and Zoning Commission will meet on November 4,
        2025 at 6:00 PM at Council

        and Court Building, 510 W. 9th Street. The City of Georgetown is
        committed to compliance with the Americans with Disabilities Act (ADA).
        If you

        require assistance in participating at a public meeting due to a
        disability, as defined under the ADA,

        reasonable assistance, adaptations, or accommodations will be provided
        upon request. Please contact the

        City Secretary's Office, at least three (3) days prior to the scheduled
        meeting date, at (512) 930-3652 or

        City Hall at 808 Martin Luther King Jr. Street, Georgetown, TX 78626 for
        additional information; TTY users

        route through Relay Texas at 711. Notice of Cancellation

        This regularly scheduled meeting of the Board is cancelled. Please check
        the posted agendas for next

        month's meeting. Certificate of Posting

        Certificate of Posting

        I, Robyn
      - >-
        for Wednesday, November 12th

        at 7:05 p.m. What you want? This meeting is being recorded. report
        anything. I have

        Yeah. agenda

        but there were other items

        >> that didn't get to this print Right. >> Caught you off guard there.
        >> I know you did. I'm not. Oh, so it

        worked very well. >> what did what did we end up

        because of the day? >> that's all right. You're fine. >> All right. So,
        we're still going to go

        a wedding for

        I think we're gonna

        want to go. All right. No problem. 1.7. First one is Parker Hill

        Well, it's already been

        Conservation Commission. Yeah. And since it's not supposed to be

        what snacks,

        >> By the way, I I did autographs. put your

        your name on your agenda and stuff and

        You mind just announcing

        that you've arrived and what time? Did provide? Guess we should wait.
        kind of that was

        >> right. So what doesn't go into the

        general account instead

        of meeting

        I thought we had a

        Can you read it off? Oh, you

        You just repeat the number.
pipeline_tag: sentence-similarity
library_name: sentence-transformers

SentenceTransformer based on google-bert/bert-base-uncased

This is a sentence-transformers model finetuned from google-bert/bert-base-uncased. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.

Model Details

Model Description

  • Model Type: Sentence Transformer
  • Base model: google-bert/bert-base-uncased
  • Maximum Sequence Length: 256 tokens
  • Output Dimensionality: 768 dimensions
  • Similarity Function: Cosine Similarity

Model Sources

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 256, 'do_lower_case': False, 'architecture': 'BertModel'})
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
)

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("ar9av/tsdae-civic-bert")
# Run inference
sentences = [
    "right o'clock Oh Jack here . Man brought team 3rd November . going'll to . We Pledge of and . And we got guests Manager Brantley'll of . the . I appeal flag the United States of and to Republic which,, for . Let . God, come before this grateful live wonderful community We serve our community members in our respective capacities morning and give us eyes and full hearts, Lord, as handle business Thank you your, In Christ name amen Thank Price the pledge . First item is",
    "All right, it's nine o'clock. Oh, Jack's here too. Man, y'all brought the whole team. 9 o'clock, November 3rd, November already. Gosh. Time keeps on going. We'll call the meeting to order. We'll open with the Pledge of Allegiance and prayer. And since we've got special guests, I'll ask Town Manager Brantley Price if he'll lead us in the Pledge of Allegiance. And I'll say the prayer. I appeal to the flag of the United States of America and to the Republic for which it stands, one nation under God, indivisible, with liberty and justice for all. Let's pray together. God, we come before you this morning with grateful hearts to live in such a wonderful community. We're grateful for the opportunity to serve our community members in our respective capacities here this morning. Be with us and give us clear eyes and full hearts, Lord, as we handle the people's business. Thank you for your many, many blessings. In Christ's name, amen. Amen. Thank you, Manager Price, for the pledge. First item is",
    "for Wednesday, November 12th\nat 7:05 p.m. What you want? This meeting is being recorded. report anything. I have\nYeah. agenda\nbut there were other items\n>> that didn't get to this print Right. >> Caught you off guard there. >> I know you did. I'm not. Oh, so it\nworked very well. >> what did what did we end up\nbecause of the day? >> that's all right. You're fine. >> All right. So, we're still going to go\na wedding for\nI think we're gonna\nwant to go. All right. No problem. 1.7. First one is Parker Hill\nWell, it's already been\nConservation Commission. Yeah. And since it's not supposed to be\nwhat snacks,\n>> By the way, I I did autographs. put your\nyour name on your agenda and stuff and\nYou mind just announcing\nthat you've arrived and what time? Did provide? Guess we should wait. kind of that was\n>> right. So what doesn't go into the\ngeneral account instead\nof meeting\nI thought we had a\nCan you read it off? Oh, you\nYou just repeat the number.",
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.8891, 0.8695],
#         [0.8891, 1.0000, 0.8283],
#         [0.8695, 0.8283, 1.0000]])

Training Details

Training Dataset

Unnamed Dataset

  • Size: 10,000 training samples
  • Columns: sentence_0 and sentence_1
  • Approximate statistics based on the first 1000 samples:
    sentence_0 sentence_1
    type string string
    details
    • min: 3 tokens
    • mean: 91.75 tokens
    • max: 202 tokens
    • min: 13 tokens
    • mean: 223.56 tokens
    • max: 256 tokens
  • Samples:
    sentence_0 sentence_1
    right I call this town council to order on Recognize is a quorum all those who attendance in those are in online . hello Davis are tonight . Thanks, I We having you . and expeditious tonight a big game JMU at . like have just a wo we've had two works who their a of for Our are with them time Ms. we have?? .? Here?? Here . Mr. Hunter? Here Hardy All right, I'd like to call this town council meeting to order on this November 12, 2025. Recognize there is a quorum present. Welcome all those who are in attendance in person and those who are tuned in online. A special hello to Dr. Davis's local and state government class students who are here tonight. Thanks for coming, although I think you were probably told you had to. We appreciate having you. We'll try and be expeditious in the people's business tonight because I know there's a big game later this evening between Longwood and JMU here at home. I'd also like to have just a moment. I won't mention names, but we've had two of our public works employees who lost their wives here very recently. And so we'll just have a brief moment of silence for them. Thank you. Our prayers and our hearts are with them at this difficult time. Ms. McKay, can we have a roll call, please? Mrs. Amos? Here. Mr. Reed? Here. Mr. Dwyer? Here. Mr. Parrott? Here. Mr. Yoland. Here. Mr. Hunter? Here. Mr. Hardy
    everyone November the City Columbia Board of Chair for meeting like introduce the members: Harding'm, Davis Whittle, Sidney Bang, Duvall also to introduce the staff the, Andrew, Board, Erica Hyan, Deputy and Madeline Land . is special, appeals . for the record, wishing and come the . No can floor When come the podium state your and speak the because meeting is recorded Applicants the board Welcome, everyone, to the November meeting of the City of Columbia Board of Zoning Appeals. I am Catherine Fenner, Chair for the Board, and will be serving as the chair for today's meeting. I would like to introduce the other members of the board: Josh Harding, I'm sorry, Davis Whittle, Sidney Lanham, Jonathan Bang, and Sherard Duvall. I would also like to introduce the staff that assists the board, Andrew Livingood, Zoning Board Administrator, Erica Hyan, Deputy Zoning Administrator, and Madeline Bowden, Land Use Board Coordinator. The board is charged with hearing applications for special exceptions, variances, and administrative appeals. All testimony is recorded for the record, and anyone wishing to speak will need to be sworn in and come to the podium to speak. No testimony can be taken from the floor. When you come to the podium, state your name and please speak clearly into the microphone because this meeting is being recorded. Applicants with cases before the board are allotted
    Corporation 7:30 WEDC Room 250 Highway Texas TO & PLEDGE OF ON ITEMS member the may Board not Agenda of the fill out a form meeting . that comments limited minutes for, six In addition, is not allowed to converse deliberate take on any presented CONSENT AGENDA matters Agenda are be routine by Board will be will not of items . discussion desired, that item will removed from the separately . act upon Wylie Economic Development Corporation
    Board Regular Meeting
    November 19, 2025 – 7:30 AM
    WEDC Office Conference Room - 250 South Highway 78, Wylie, Texas
    75098





    CALL TO ORDER
    INVOCATION & PLEDGE OF ALLEGIANCE
    COMMENTS ON NON-AGENDA ITEMS
    Any member of the public may address Board regarding an item that is not listed on the Agenda. Members of the public must
    fill out a form prior to the meeting in order to speak. Board requests that comments be limited to three minutes for an individual,
    six minutes for a group. In addition, Board is not allowed to converse, deliberate or take action on any matter presented during
    citizen participation. CONSENT AGENDA
    All matters listed under the Consent Agenda are considered to be routine by the Board and will be enacted by one motion. There will not be separate discussion of these items. If discussion is desired, that item will be removed from the Consent Agenda
    and will be considered separately. A. Consider and act upon appr
  • Loss: DenoisingAutoEncoderLoss

Training Hyperparameters

Non-Default Hyperparameters

  • num_train_epochs: 1
  • multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand
  • overwrite_output_dir: False
  • do_predict: False
  • eval_strategy: no
  • prediction_loss_only: True
  • per_device_train_batch_size: 8
  • per_device_eval_batch_size: 8
  • per_gpu_train_batch_size: None
  • per_gpu_eval_batch_size: None
  • gradient_accumulation_steps: 1
  • eval_accumulation_steps: None
  • torch_empty_cache_steps: None
  • learning_rate: 5e-05
  • weight_decay: 0.0
  • adam_beta1: 0.9
  • adam_beta2: 0.999
  • adam_epsilon: 1e-08
  • max_grad_norm: 1
  • num_train_epochs: 1
  • max_steps: -1
  • lr_scheduler_type: linear
  • lr_scheduler_kwargs: {}
  • warmup_ratio: 0.0
  • warmup_steps: 0
  • log_level: passive
  • log_level_replica: warning
  • log_on_each_node: True
  • logging_nan_inf_filter: True
  • save_safetensors: True
  • save_on_each_node: False
  • save_only_model: False
  • restore_callback_states_from_checkpoint: False
  • no_cuda: False
  • use_cpu: False
  • use_mps_device: False
  • seed: 42
  • data_seed: None
  • jit_mode_eval: False
  • bf16: False
  • fp16: False
  • fp16_opt_level: O1
  • half_precision_backend: auto
  • bf16_full_eval: False
  • fp16_full_eval: False
  • tf32: None
  • local_rank: 0
  • ddp_backend: None
  • tpu_num_cores: None
  • tpu_metrics_debug: False
  • debug: []
  • dataloader_drop_last: False
  • dataloader_num_workers: 0
  • dataloader_prefetch_factor: None
  • past_index: -1
  • disable_tqdm: False
  • remove_unused_columns: True
  • label_names: None
  • load_best_model_at_end: False
  • ignore_data_skip: False
  • fsdp: []
  • fsdp_min_num_params: 0
  • fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
  • fsdp_transformer_layer_cls_to_wrap: None
  • accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
  • parallelism_config: None
  • deepspeed: None
  • label_smoothing_factor: 0.0
  • optim: adamw_torch
  • optim_args: None
  • adafactor: False
  • group_by_length: False
  • length_column_name: length
  • project: huggingface
  • trackio_space_id: trackio
  • ddp_find_unused_parameters: None
  • ddp_bucket_cap_mb: None
  • ddp_broadcast_buffers: False
  • dataloader_pin_memory: True
  • dataloader_persistent_workers: False
  • skip_memory_metrics: True
  • use_legacy_prediction_loop: False
  • push_to_hub: False
  • resume_from_checkpoint: None
  • hub_model_id: None
  • hub_strategy: every_save
  • hub_private_repo: None
  • hub_always_push: False
  • hub_revision: None
  • gradient_checkpointing: False
  • gradient_checkpointing_kwargs: None
  • include_inputs_for_metrics: False
  • include_for_metrics: []
  • eval_do_concat_batches: True
  • fp16_backend: auto
  • push_to_hub_model_id: None
  • push_to_hub_organization: None
  • mp_parameters:
  • auto_find_batch_size: False
  • full_determinism: False
  • torchdynamo: None
  • ray_scope: last
  • ddp_timeout: 1800
  • torch_compile: False
  • torch_compile_backend: None
  • torch_compile_mode: None
  • include_tokens_per_second: False
  • include_num_input_tokens_seen: no
  • neftune_noise_alpha: None
  • optim_target_modules: None
  • batch_eval_metrics: False
  • eval_on_start: False
  • use_liger_kernel: False
  • liger_kernel_config: None
  • eval_use_gather_object: False
  • average_tokens_across_devices: True
  • prompts: None
  • batch_sampler: batch_sampler
  • multi_dataset_batch_sampler: round_robin
  • router_mapping: {}
  • learning_rate_mapping: {}

Training Logs

Epoch Step Training Loss
0.4 500 4.3532
0.8 1000 3.4547

Framework Versions

  • Python: 3.11.10
  • Sentence Transformers: 5.2.0
  • Transformers: 4.57.3
  • PyTorch: 2.4.1+cu124
  • Accelerate: 1.12.0
  • Datasets: 4.4.2
  • Tokenizers: 0.22.1

Citation

BibTeX

Sentence Transformers

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}

DenoisingAutoEncoderLoss

@inproceedings{wang-2021-TSDAE,
    title = "TSDAE: Using Transformer-based Sequential Denoising Auto-Encoderfor Unsupervised Sentence Embedding Learning",
    author = "Wang, Kexin and Reimers, Nils and Gurevych, Iryna",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
    month = nov,
    year = "2021",
    address = "Punta Cana, Dominican Republic",
    publisher = "Association for Computational Linguistics",
    pages = "671--688",
    url = "https://arxiv.org/abs/2104.06979",
}